Pseudo-Labeling With Large Language Models for Multi-Label Emotion Classification of French Tweets

Autor: Usman Malik, Simon Bernard, Alexandre Pauchet, Clement Chatelain, Romain Picot-Clemente, Jerome Cortinovis

Publikováno v: IEEE Access, Vol 12, Pp 15902-15916 (2024)

This study proposes a novel semi-supervised multi-label emotion classification approach for French tweets based on pseudo-labeling. Human subjectivity in emotional expression makes it difficult for a machine to learn. Therefore, it necessitates train

Externí odkaz: https://doaj.org/article/01e2924da23b4cedb50d38dc2132ec1e

Saagie at Semeval-2019 Task 5: From Universal Text Embeddings and Classical Features to Domain-specific Text Classification

Autor: Romain Picot-Clémente, Miriam Benballa, Sebastien Collet

Publikováno v: SemEval@NAACL-HLT

This paper describes our contribution to SemEval 2019 Task 5: Hateval. We propose to investigate how domain-specific text classification task can benefit from pretrained state of the art language models and how they can be combined with classical han

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a95afaa85a4da5c7233ac08e28e87727
https://doi.org/10.18653/v1/s19-2083

Social Interactions vs Revisions, What Is Important for Promotion in Wikipedia?

Autor: Romain Picot-Clémente, Cécile Bothorel, Nicolas Jullien

Publikováno v: ASONAM 2015 : IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
ASONAM 2015 : IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Aug 2015, Paris, France. pp.888-893, ⟨10.1145/2808797.2810063⟩
ASONAM
ASONAM 2015 : IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Aug 2015, Paris, France. pp.888-893, 2015, 〈10.1145/2808797.2810063〉

In epistemic community, people are said to be selected on their knowledge contribution to the project (articles, codes, etc.) However, the socialization process is an important factor for inclusion, sustainability as a contributor, and promotion. Fin

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::431bceba51821f4bcba6e5ba6d5af77b
https://hal.science/hal-01243183

Towards Intention, Contextual and Social Based Recommender System

Autor: Philippe Lenca, Romain Picot-Clémente, Cécile Bothorel

Publikováno v: Advanced Approaches to Intelligent Information and Database Systems ISBN: 9783319055022

This article proposes a recommender system of shopping places for users in mobility with given intentions. It considers the user intention, her context and her location-based social network for providing recommendations using a method based on associ

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b06734e2b4083ad8e8c540a76a8faef7
https://doi.org/10.1007/978-3-319-05503-9_1